Video contrast abnormity detection method and device
A contrast and anomaly technology, applied in the field of video contrast anomaly detection methods and devices, can solve problems such as low video contrast accuracy, and achieve the effects of improving accuracy and accurate detection results
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0093] Example 1:
[0094] figure 2 This is a flowchart of a method for detecting anomalous video contrast provided in Embodiment 1 of the present invention, which specifically includes the following processing steps:
[0095] Step 201: Obtain a video image to be detected from a video to be detected.
[0096] Step 202: Use a preset extraction method to extract the brightness feature information of the video image to be detected.
[0097] Step 203: Match the brightness feature information with the first type of classification feature information to obtain a first matching result, where the first type of classification feature information is based on pre-extracting a plurality of high contrast abnormalities using the preset extraction method. The video image corresponds to the multiple brightness feature information obtained.
[0098] In this step, the support vector machine (SVM) method can be used to determine the classification feature information. Specifically, the SVM method can be...
Example Embodiment
[0124] Example 2:
[0125] image 3 This is a flowchart of a method for detecting anomalous video contrast provided in Embodiment 2 of the present invention, which specifically includes the following processing steps:
[0126] Step 301: Obtain a video image to be detected from the video to be detected.
[0127] Step 302: Use a preset extraction method to extract the brightness feature information of the video image to be detected.
[0128] Step 303: Match the brightness feature information with the first type of classification feature information to obtain a first matching result, where the first type of classification feature information is based on pre-extracting a plurality of high contrast abnormalities based on the preset extraction method. The video image corresponds to the multiple brightness feature information obtained.
[0129] In this step, the SVM method can be used to determine the classification feature information. Specifically, the SVM method can be used to analyze and ...
Example Embodiment
[0143] Example 3:
[0144] Figure 4 This is a flowchart of a method for detecting anomalous video contrast provided in Embodiment 3 of the present invention, which specifically includes the following processing steps:
[0145] Step 401: Obtain a video image to be detected from a video to be detected.
[0146] Step 402: For each value in the brightness value range, determine the number of pixels with the brightness value of the value in the to-be-detected video image as the number of pixels corresponding to the value.
[0147] Step 403: From all the values in the brightness value range, determine that the number of corresponding pixels is not less than the maximum value and the minimum value of the preset number threshold.
[0148] In this step, for the number of pixels G1 corresponding to each value in the brightness value range, the relationship between G1 and the preset number threshold TH1 can be compared. When G1 is less than TH1, the value of G1 is set to 0, and when G1 is not l...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap